Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Cloudlflare builds OAuth with Claude and publishes all the prompts

github.com

Post reply on HN
Print view View original

211–220 of 552 posts

Re: Cloudlflare builds OAuth with Claude and publishes all the prompts

#211

Post by bufferoverflow »

weinzierl wrote: post #175

"I thoughts LLMs were glorified Markov chain generators" "the code actually looked pretty good. Not perfect, but I just told the AI to fix things, and it did. I was shocked." These two views are by no means mutually exclusive. I find LLMs extremely useful and still believe they are glorified Markov generators. The take away should be that that is all you need and humans likely are nothing more than that.

> I find LLMs extremely useful and still believe they are glorified Markov generators.

Then you should be able to make a markov chain generator without deep neural nets, and it should be on the same level of performance as current LLMs.

But we both know you can't.

Re: Cloudlflare builds OAuth with Claude and publishes all the prompts

#212

Post by Workaccount2 »

cpursley wrote: post #204
stego-tech wrote: post #110

Earlier quoted context omitted.

> Vibe-coding won't be a net creativity gain to a researcher affected by vibe-immigration-policy, vibe-grant-availability, and vibe-firings, for all of which the unpredictability is a punitive design goal. Quite literally this is what I’m trying to get at with my resistance to LLM adoption in the current environment. We’re not using it to do hard work, we’re throwing it everywhere in an intentional decision to dumb d…

That’s one perspective, but it’s wrong and typical gatekeeping (do you have a software degree by any chance?). People had the same attitude towards open source tooling and low code frameworks - god forbid someone not certified and ordained build a solution in something other than Java... AI code tools are allowing people to build things they couldn't before due to lack of skillset, time or budget. I’ve seen all sorts…

>My brother for example built a thing with Microsoft copilot that helped automate more in his manufacturing facility (used to be paper).

I have harped on this endlessly as a non-programmer working a non-tech job, with 7 "vibe-coded" programs now being used daily by people at my company.

I am sorry, but the tech world is completely missing the forest for the trees here. LLM's are talked about purely as tools that were created to help devs. Some love them, some hate them, but pretty much all of them seem unaware that LLMs allow non-tech people to automate tasks with a computer without having to go through a 3rd-party-created interface.

So yea, maybe Claude is useless troubleshooting your cloud platform. But it certainly isn't useless in helping me forgo a cloud platform by setting up a simple local database to use instead.

Re: Cloudlflare builds OAuth with Claude and publishes all the prompts

#213

Post by alastairr »

paxys wrote: post #65
spiderice wrote: post #59

Earlier quoted context omitted.

But there very well might be a time very soon where human's no longer offer economic value to the software engineering process. If you could (and currently you can't) pay an AI $10k/year to do what a human could do in a year, why would you pay the human 6 figures? Or even $20k? Nobody is claiming that human's won't have jobs simply because "we have accomplished everything this is to do". It's that humans will offer z…

And there might be a giant asteroid that strikes the earth a few years down the line ending human civilization. If there is some magic $10k AI that can fully replace a $200k software engineer then I'd love to see it. Until that happens this entire discussion is science fiction.

You don’t need to completely replace a whole 200k engineer. You just need to increase each engineer’s productivity sufficiently that you can reduce the total number of engineers in your company.

Re: Cloudlflare builds OAuth with Claude and publishes all the prompts

#214

Post by cpursley »

Workaccount2 wrote: post #212
cpursley wrote: post #204

Earlier quoted context omitted.

That’s one perspective, but it’s wrong and typical gatekeeping (do you have a software degree by any chance?). People had the same attitude towards open source tooling and low code frameworks - god forbid someone not certified and ordained build a solution in something other than Java... AI code tools are allowing people to build things they couldn't before due to lack of skillset, time or budget. I’ve seen all sorts…

>My brother for example built a thing with Microsoft copilot that helped automate more in his manufacturing facility (used to be paper). I have harped on this endlessly as a non-programmer working a non-tech job, with 7 "vibe-coded" programs now being used daily by people at my company. I am sorry, but the tech world is completely missing the forest for the trees here. LLM's are talked about purely as tools that were…

Yep, and it allows them to build POCs that they can pass to "real" devs in a way that was not possible before.

Re: Cloudlflare builds OAuth with Claude and publishes all the prompts

#215

Post by lanthissa »

spiderice wrote: post #59
paxys wrote: post #52

Earlier quoted context omitted.

Increased productivity means increased opportuntity. There isn't going to be a time (at least not anytime soon) when we can all sit back and say "yup, we have accomplished everything there is to do with software and don't need more engineers".

But there very well might be a time very soon where human's no longer offer economic value to the software engineering process. If you could (and currently you can't) pay an AI $10k/year to do what a human could do in a year, why would you pay the human 6 figures? Or even $20k? Nobody is claiming that human's won't have jobs simply because "we have accomplished everything this is to do". It's that humans will offer z…

it doesn't even have to be that. software engineer used to be a medium pay job, theres no law of the universe that says it cant go back to that.

Re: Cloudlflare builds OAuth with Claude and publishes all the prompts

#216

Post by steveklabnik »

baq wrote: post #185
steveklabnik wrote: post #174

Earlier quoted context omitted.

One recent post I read about improving the discourse (which I seem to have lost the link...) agrees, but in a different way: adding a "capable vs not" axis. that is, "I believe AI is good enough to replace humans, and I am pro" is different than "I believe AI is good enough to replace humans, and I am against" and while "I believe AI is not good enough to replace humans, and I am pro" is a weird position to take, "I…

> "I believe AI is not good enough to replace humans, and I am pro" is a weird position to take Huh? The recipe how to be in this position is literally in the readme of the linked project. You don’t even have to believe it, you just have to work it.

I mean at the most extreme: that it can NEVER do so. Someone who holds this position would point to commits like https://news.ycombinator.com/item?id=44159659

Re: Cloudlflare builds OAuth with Claude and publishes all the prompts

#217

Post by steveklabnik »

jakeydus wrote: post #195
steveklabnik wrote: post #174

Earlier quoted context omitted.

One recent post I read about improving the discourse (which I seem to have lost the link...) agrees, but in a different way: adding a "capable vs not" axis. that is, "I believe AI is good enough to replace humans, and I am pro" is different than "I believe AI is good enough to replace humans, and I am against" and while "I believe AI is not good enough to replace humans, and I am pro" is a weird position to take, "I…

> "I believe AI is not good enough to replace humans, and I am pro" is a weird position to take I think that's just the opinion of someone who doesn't think AI currently lives up to the hype but is optimistic about developing it further, not really that weird of a position in my opinion. Personally I'm moving more into the "I think AI is good enough to replace humans, and I am against" category.

Yeah, I meant like, at the full extreme of "and it never will". Someone with the position you describe wouldn't be at the far end, but somewhere closer to the middle.

Re: Cloudlflare builds OAuth with Claude and publishes all the prompts

#218

Post by viktorcode »

diggan wrote: post #40
infinitebattery wrote: post #23

From this commit: https://github.com/cloudflare/workers-oauth-provider/commit/... === "Fix Claude's bug manually. Claude had a bug in the previous commit. I prompted it multiple times to fix the bug but it kept doing the wrong thing. So this change is manually written by a human. I also extended the README to discuss the OAuth 2.1 spec problem." === This is super relatable to my experience trying to use these AI tool…

> They can get halfway there and then struggle immensely. Restart the conversation from scratch. As soon as you get something incorrect, begin from the beginning. It seems to me like any mistake in a messages chain/conversation instantly poisons the output afterwards, even if you try to "correct" it. So if something was wrong at one point, you need to go back to the initial message, and adjust it to clarify the promp…

It can be done, but for my environment the sum of all prompts that I end up typing to get the right result ends up being longer than the actual code.

So now I'm using LLMs as crapshoot machines for generating ideas which I then implement manually

Re: Cloudlflare builds OAuth with Claude and publishes all the prompts

#219

Post by ronsor »

bufferoverflow wrote: post #211
weinzierl wrote: post #175

"I thoughts LLMs were glorified Markov chain generators" "the code actually looked pretty good. Not perfect, but I just told the AI to fix things, and it did. I was shocked." These two views are by no means mutually exclusive. I find LLMs extremely useful and still believe they are glorified Markov generators. The take away should be that that is all you need and humans likely are nothing more than that.

> I find LLMs extremely useful and still believe they are glorified Markov generators. Then you should be able to make a markov chain generator without deep neural nets, and it should be on the same level of performance as current LLMs. But we both know you can't.

You can, but it will require far more memory than any computer has.

Re: Cloudlflare builds OAuth with Claude and publishes all the prompts

#220

Post by freedomben »

kentonv wrote: post #179
freedomben wrote: post #140

Earlier quoted context omitted.

What tools did you use for the vibe coding an Android app? And was it able to do the UI stuff too? I've wanted to do this but am not sure how to get started. For example, should I generate a new app in Android Studio and then point Claude Code at it? Or can I ask Claude Code (or another agent) to start it from scratch? (in the past that did not work, but I'm curious if it's just a PEBKAC error)

I used Claude Code. I actually just asked it what tools I needed for a CLI-driven build, and it told me what to install (or even installed it for me in some cases). I basically didn't read any documentation, just asked Claude what I should do.

Amazing, thank you!

Edit: Holy shit, in 30 minutes I used Claude code to make a simple PDF viewer app, and it totally works. I did have to prompt it through the process quite a bit, including correcting some obvious flubs, but I'm super impressed.

I didn't even have to install the android dev tools because I asked it to generate a Dockerfile in which to do the build, and a simple script to copy the apk out when done :-D

Post reply on HN